AI Engineer Production Track: Deploy LLMs & Agents at Scale (Udemy.com)
Deploy AI to AWS, GCP, Azure, Vercel with MLOps, Bedrock, SageMaker, RAG, Agents, MCP: scalable, secure and observable.
Created by: Ligency
Last updated June 2026
What you will learn
- Deploy SaaS LLM apps to production on Vercel, AWS, Azure, and GCP, using Clerk
- Design cloud architectures with Lambda, S3, CloudFront, SQS, Route 53, App Runner and API Gateway
- Integrate with Amazon Bedrock and SageMaker, and build with GPT-5, Claude 4, OSS, AWS Nova and HuggingFace
- Rollout to Dev, Test and Prod automatically with Terraform and ship continuously via GitHub Actions
- Deliver enterprise-grade AI solutions that are scalable, secure, monitored, explainable, observable, and controlled with guardrails.
- Create Multi-Agent systems and Agentic Loops with Amazon Bedrock AgentCore and Stands Agents
Course Description
This is the course that more of my students have asked for than any other course — put together.
One student called it:
“The missing course in AI.”
This course is for:
Entrepreneurs
Enterprise engineers
…and everyone in between.
It’s not just about RAG — although we’ll work with RAG.
It’s not just about Agents — but there will be many Agents.
It’s not just about MCP — but yes, there will be plenty of MCP too.
This course is about:
RAG, Agents, MCP, and so much more… deployed to production.
Live.
Enterprise-grade.
Scalable, resilient, secure, monitored — and explained.
You’ll ship real-world, production-grade AI with LLMs and agents across Vercel, AWS, GCP, and Azure, going deepest on AWS.
Across four weeks you’ll take four products to production:
Week 1
You’ll launch a Next.js SaaS product on Vercel and AWS,
with AWS App Runner and Clerk for user management and subscriptions.
Week 2
You’ll become an AI platform engineer on AWS,
deploying serverless infrastructure using:
Lambda, Bedrock, API Gateway, S3, CloudFront, Route 53
Write Infrastructure as Code with Terraform
Set up CI/CD pipelines with GitHub Actions
— for hands-free deployments and one-click promotions.
Week 3
You’ll gain broad industry skills for GenAI in production:
Deploy a Cyber Security Analyst agent with MCP to Azure & GCP
Stand up SageMaker inference
Build data ingest to S3 vectors
Deploy a Researcher Agent using OpenAI OSS models on Bedrock + MCP
Week 4
You’ll go fully agentic in production:
Architect multi-agent systems with:
Aurora Serverless, Lambda, SQS
JWT-authenticated CloudFront frontends
LangFuse observability
Overview of AWS Agent Core
By the end, you’ll know how to:
Pick the right architecture
Lock down security
Monitor costs
Deliver continuous updates
Everything needed to run scalable, reliable AI apps in production.
Course sections (Weeks & Projects)
Week 1
SaaS App Live in Production with Vercel, AWS, Next.js, Clerk, App Runner
Project: SaaS Healthcare App
Week 2
AI Platform Engineering on AWS with Bedrock, Lambda, API Gateway, Terraform, CI/CD
Project: Digital Twin Mk II
Week 3
Gen AI in Production with Azure, GCP, AWS SageMaker, S3 Vectors, MCP
Project: Cybersecurity Analyst
Week 4
Agentic AI in Production: Build and deploy a Multi-Agent System on AWS (Aurora Serverless, Lambda, SQS),
with LangFuse and Bedrock AgentCore
Capstone Project: SaaS Financial Planner
Instructor Details
- 4.7 Rating
3,779 Reviews
Ligency
Join 4M+ learners who study with Ligency.
With a 4.6 instructor rating, >1M reviews, and 127 courses in 12 languages, we help engineers, leaders, and teams master the skills that power today’s AI revolution - then ship real results.
We start where the real world starts: with large language models and the products they power. You’ll learn the foundations of AI and Generative AI (gen AI), then ship production-grade systems - chatbots, copilots, automations, and AI agents. We go deep on LLM engineering: retrieval (RAG), evaluation, observability, safety, and the patterns teams use to run agentic systems at scale.
Our stack is practical and current. You’ll prototype fast with Python, LangChain, and LangGraph; explore models from OpenAI, Gemini, and Claude (including Claude Code); fine-tune and serve with Hugging Face and Ollama; and take it to production on AWS - from Bedrock to event-driven services. Need automation? We wire it together with n8n, clean interfaces, and CI/CD. Along the way you’ll master prompt engineering that holds up under load.
More courses by Ligency
AI Engineer Core Track: LLM Engineering, RAG, QLoRA, Agents (2026)
4.7 (41,522 Reviews)
Provider: Udemy
Time: 33.5h
$109.99
AI Coder: Complete Claude Code & Coding Agents Course (2026)
4.6 (11,184 Reviews)
Provider: Udemy
Time: 16.3h
$19.99
AI Builder: Create Agents, Voice Agents & Automations in n8n (2026)
4.8 (4,579 Reviews)
Provider: Udemy
Time: 14.3h
$19.99
More Data Science courses
Master statistics & machine learning: intuition, math, code (2026)
4.9 (3,077 Reviews)
Provider: Udemy
Time: 38.3h
$124.99
Ciência de Dados para Empresas e Negócios (2026)
4.9 (559 Reviews)
Provider: Udemy
Time: 14.4h
$19.99
Reviews
By Guy Cole on 7/28/2026
This is my second course w/Ed. I am not a beginner, but there is still great value in this course because Ed explores options we did not take where I work. I also have taught my own courses, and it is not easy to develop and sustain a complicated and dynamic course. Ed has put in the work, I learned something and I hope you will also benefit. Buy it now.
By Abhishek Kumar singh on 7/26/2026
The material is exceptionally well‑organized, with each module building logically on the previous one, and the instructor’s clear explanations—paired with real‑world examples and hands‑on projects—made complex concepts easy to grasp; the downloadable resources (code files, cheat‑sheets, and quizzes) were up‑to‑date and incredibly useful for practice, and the active Q&A community ensured quick answers to any problems, though the video lengths could be trimmed into shorter segments and a few audio sections would benefit from clearer sound or subtitles; overall, the course provided me with concrete skills I could immediately apply to my own projects and I would highly recommend it to anyone looking to master
By Jovan Maksimoski on 7/20/2026
The course is overall great, you are provided with a great starting point to start developing your mlops skills, as expected you are faced with perks and challanges since things constantly change. The course is well paced aswell, maybe even slow at times for me but make sure you resolve all of the unexplained code and concepts with an LLM. Where I do have a problem is the last project, I was looking forward to building a complex project setting up multiple pipelines, services, resources, cloud providers all the nasty things(as the instructor would say). I was met with a project that I halfway understood and didnt know what to think of it so I just gave up dissapointed. Great course overall, could be a more complex in my opinion
By Tommy Gagne on 7/13/2026
This is a very complex course, but I often felt that the instructor did not spend enough time explaining the material in depth. For example, I would have appreciated a more detailed explanation of the Terraform files and how they work. I can read the files myself, but when I enroll in a course, I expect the instructor to walk through the code, explain the architecture, and clarify why certain decisions were made. I also would have liked much more coverage of Azure and GCP. The content is ambitious enough that the course could easily have been spread over five or six weeks, with more time dedicated to each cloud provider and infrastructure component. Another major frustration was Amazon Bedrock. This is not entirely the instructor’s fault, but my experience with the service was extremely poor. I received a “Too many tokens per day” error even though it was my first time using it. I requested quota increases, waited several weeks for approval, and ultimately asked Claude Code to refactor the project to use the OpenAI SDK instead. As a result, I did not end up testing Bedrock at all. Overall, the course contains valuable and advanced material, but it moves too quickly and would benefit greatly from slower, more detailed explanations.
By Raaj Sivaram on 5/26/2026
Excellent course once again, Ed continues to be an outstanding trainer with a very practical and engaging teaching style. The AI Engineer Production course provided valuable hands-on exposure to deploying and operationalizing AI solutions, making complex concepts easy to understand and apply in real-world scenarios. I particularly appreciate the structured approach, clarity of explanations, and the strong focus on production-ready AI engineering practices. Having now completed both the AI Engineer Core and Production tracks, I can confidently say the learning experience has been extremely valuable. I have already recommended Ed’s courses to several friends and colleagues, and I would strongly recommend them to anyone looking to build solid, practical expertise in AI and AI engineering.
By Robert Chandra Mohan Jayapaul on 5/22/2026
This course was exceptionally good and one of the best practical AI production deployment courses I’ve taken. The explanations, project structure, and real-world deployment concepts were excellent and very easy to follow. The only very minor downside was that Week 4, especially Day 4, felt a bit rushed, and some of the coding sections could have been explained in more detail. Apart from that, the course was outstanding and highly valuable for anyone looking to learn AI engineering and production deployment. Definitely a 5-star course!
By Srikanth Pasam on 5/21/2026
Fantastic course! The entire curriculum was brilliantly planned and seamlessly executed. It's clear that a lot of deep thought and intentional design went into structuring the material. Beyond the content itself, your enthusiasm made the learning experience incredibly engaging—it brought a smile to my face during every module, and your genuine enjoyment in recording these sessions really shines through. Thank you for delivering such an exceptional course. This goes far beyond just teaching AI; it delivers real, holistic value.
By Konstantinos Kontostathis on 5/9/2026
Exceptional course and exceptional Ed as always (and as expected). The only thing that bothered me was the many issues with AWS (e.g. Amazon Bedrock) that prevented me from implementing everything as instructed in the course. Personally, I wouldn't have selected a cloud provider with so much difficulty and so many issues... Apart from that, Ed indeed replies and always helps, I learned a lot regarding Terraform and various platforms/providers. I knew all these things 2 years ago, I wouldn't have lost my former job... Ed, respect!
By Aristide Spagnolo on 4/30/2026
Ed is extremely good at explaining complex stuff in a very engaging way and also to get to the point without loosing in details that you can develop later by yourself. I had before just little knowledge of DevOps and MLops and this course helped me to get an overview on all I have missed, but with a flavour of AI. I have done other courses by Ed to understand how llm works, but with this one you can really start to deploy your application professionally! Thanks Ed!
By Sonya Ling on 3/29/2026
Ed, Thanks a lot to put together such a wondeful materials. I feel that I extend myself to DevOp and full stack engineer domains. I learned more and more. It's a difficult course. Screens might change from the time you shot your videos. Need to improvise and figure them out as things go. I wish that I have time to dwindle it longer. I will take next on AI coding that has become a necessity for job application. One thing that I learned from you is that: I don't need to be expert on everything. I can extend my capability to accomplish a full stack project, including DevOp if I know how to make best use of Claude codes. Will come back to review and finish assignments after that. Hopefully, I have some progress on job applications too. Thanks again!!
Quality Score
No CourseDuck member has rated this course yet. Taken it? Give each part a thumbs up or down.
Overall Score : 94 / 100









